RESUMO
BACKGROUND: Tuberculomas are prevalent in developing countries and demonstrate variable signals on MRI resulting in the overlap of the conventional imaging phenotype with other entities including glioma and brain metastasis. An accurate MRI diagnosis is important for the early institution of anti-tubercular therapy, decreased patient morbidity, mortality, and prevents unnecessary neurosurgical excision. This study aims to assess the potential of radiomics features of regular contrast images including T1W, T2W, T2W FLAIR, T1W post contrast images, and ADC maps, to differentiate between tuberculomas, high-grade-gliomas and metastasis, the commonest intra parenchymal mass lesions encountered in the clinical practice. METHODS: This retrospective study includes 185 subjects. Images were resampled, co-registered, skull-stripped, and zscore-normalized. Automated lesion segmentation was performed followed by radiomics feature extraction, train-test split, and features reduction. All machine learning algorithms that natively support multiclass classification were trained and assessed on features extracted from individual modalities as well as combined modalities. Model explainability of the best performing model was calculated using the summary plot obtained by SHAP values. RESULTS: Extra tree classifier trained on the features from ADC maps was the best classifier for the discrimination of tuberculoma from high-grade-glioma and metastasis with AUC-score of 0.96, accuracy-score of 0.923, Brier-score of 0.23. CONCLUSION: This study demonstrates that radiomics features are effective in discriminating between tuberculoma, metastasis, and high-grade-glioma with notable accuracy and AUC scores. Features extracted from the ADC maps surfaced as the most robust predictors of the target variable.
RESUMO
The hypothalamus, composed of several nuclei, is essential for maintaining our body's homeostasis. The arcuate nucleus (ARC), located in the mediobasal hypothalamus, contains neuronal populations with eminent roles in energy and glucose homeostasis as well as reproduction. These neuronal populations are of great interest for translational research. To fulfill this promise, we used a robotic cell culture platform to provide a scalable and chemically defined approach for differentiating human pluripotent stem cells (hPSCs) into pro-opiomelanocortin (POMC), somatostatin (SST), tyrosine hydroxylase (TH) and gonadotropin-releasing hormone (GnRH) neuronal subpopulations with an ARC-like signature. This robust approach is reproducible across several distinct hPSC lines and exhibits a stepwise induction of key ventral diencephalon and ARC markers in transcriptomic profiling experiments. This is further corroborated by direct comparison to human fetal hypothalamus, and the enriched expression of genes implicated in obesity and type 2 diabetes (T2D). Genome-wide chromatin accessibility profiling by ATAC-seq identified accessible regulatory regions that can be utilized to predict candidate enhancers related to metabolic disorders and hypothalamic development. In depth molecular, cellular, and functional experiments unveiled the responsiveness of the hPSC-derived hypothalamic neurons to hormonal stimuli, such as insulin, neuropeptides including kisspeptin, and incretin mimetic drugs such as Exendin-4, highlighting their potential utility as physiologically relevant cellular models for disease studies. In addition, differential glucose and insulin treatments uncovered adaptability within the generated ARC neurons in the dynamic regulation of POMC and insulin receptors. In summary, the establishment of this model represents a novel, chemically defined, and scalable platform for manufacturing large numbers of hypothalamic arcuate neurons and serves as a valuable resource for modeling metabolic and reproductive disorders.
RESUMO
Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin-stained tumor slides for precision oncology. We present ENLIGHT-DeepPT, an indirect two-step approach consisting of (1) DeepPT, a deep-learning framework that predicts genome-wide tumor mRNA expression from slides, and (2) ENLIGHT, which predicts response to targeted and immune therapies from the inferred expression values. We show that DeepPT successfully predicts transcriptomics in all 16 The Cancer Genome Atlas cohorts tested and generalizes well to two independent datasets. ENLIGHT-DeepPT successfully predicts true responders in five independent patient cohorts involving four different treatments spanning six cancer types, with an overall odds ratio of 2.28 and a 39.5% increased response rate among predicted responders versus the baseline rate. Notably, its prediction accuracy, obtained without any training on the treatment data, is comparable to that achieved by directly predicting the response from the images, which requires specific training on the treatment evaluation cohorts.
RESUMO
Background and Aims: Pulsed radiofrequency (PRF) of the saphenous nerve (SN) has shown effective pain relief in knee pain because of knee osteoarthritis (KOA). The adductor canal (AC) contains other sensory nerves innervating the medial part of the knee joint apart from SN. We compared the PRF of SN within and outside the AC for their quality and duration of pain relief in knee osteoarthritis of the medial compartment (KOA-MC). Material and Methods: We conducted a randomized prospective study in 60 patients with anteromedial knee pain because of KOA-MC. Patients in group A received PRF-SN, and those in group B received PRF-AC. The primary objectives were comparison of pain by Visual Analog Scale (VAS) scores and changes in quality of daily living by Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) and OXFORD knee scores. The secondary objectives were comparison of analgesic requirements using Medicine Quantification Scale (MQS) scores and block-related complications. Intra-group comparison was performed by analysis of variance. Inter-group normally distributed data were assessed by Student's t-test, non-normally distributed and ordinal data were assessed by Mann-Whitney U-test, and categorical data were assessed by Chi-square test. A P value of <0.05 was considered significant. Results: VAS scores were significantly lower in Gr-B at 12 weeks. The WOMAC scores and OXFORD scores at 4, 8, 12, and 24 weeks were significantly lower in Gr-B compared to Gr-A. Conclusion: The PRF-AC provides better pain relief and functional outcome than PRF-SN; however, duration of pain relief was not significantly different.
RESUMO
In the wake of Covid pandemic, usage of surgical PPE kit by surgeons has become essential. Since reliable localization of human joints is necessary for automated understanding of surgeons activity, the first step is surgical PPE kit detection. While there exist reported works on industrial PPE kit detection, task of surgical PPE kit detection has hardly been explored. To facilitate this, we construct "Surgical-PPE" dataset with 1150 Non-PPE instances and 2656 surgeon wearing PPE kit instances. In this work, we also propose a two-stage transfer learning based end-to-end training methodology. Novelty lies in (a) novel "Surgical-PPE" dataset to detect if surgeon is wearing PPE kit or not, (b) proposed supervised contrastive combined loss function for stage-1 training, (c) proposed spatial context aware combined loss function for stage-2 training. We qualitatively illustrate the improvement of HiResCAM and XGrad-CAM explanations for the proposed methodology. We also qualitatively illustrate that feature embeddings of same class are pulled closer together compared to feature embeddings of different classes on the proposed multi-stage training methodology, using T-SNE plots. We benchmark the performance of popular existing network architectures along with the proposed methodology on "Surgical-PPE" dataset. Using proposed methodology, we achieve peak accuracy of 97.63%, precision of 97.66%, recall of 97.63%, F1-score of 97.64%, JI of 95.41% and FPR of 2.5%. We report improvement by 1.7% in terms of FPR and 2% in terms of JI compared to second best performing model (ResNext50(CE)). Owing to the proposed training methodology, an improvement of 2.62% in terms of FPR and 5% in terms of JI was observed.Clinical relevance- To understand the OT activity of the surgeon in third-person perspective, it is important to determine whether or not, the surgeon is wearing PPE kit. Hence surgical PPE kit presence detection becomes the first step towards automated surgical video analysis.
Assuntos
Aprendizagem , Cirurgiões , Humanos , Equipamento de Proteção IndividualRESUMO
Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin (H&E)-stained tumor slides for precision oncology. We present ENLIGHT-DeepPT, an approach for predicting response to multiple targeted and immunotherapies from H&E-slides. In difference from existing approaches that aim to predict treatment response directly from the slides, ENLIGHT-DeepPT is an indirect two-step approach consisting of (1) DeepPT, a new deep-learning framework that predicts genome-wide tumor mRNA expression from slides, and (2) ENLIGHT, which predicts response based on the DeepPT inferred expression values. DeepPT successfully predicts transcriptomics in all 16 TCGA cohorts tested and generalizes well to two independent datasets. Our key contribution is showing that ENLIGHT-DeepPT successfully predicts true responders in five independent patients' cohorts involving four different treatments spanning six cancer types with an overall odds ratio of 2.44, increasing the baseline response rate by 43.47% among predicted responders, without the need for any treatment data for training. Furthermore, its prediction accuracy on these datasets is comparable to a supervised approach predicting the response directly from the images, which needs to be trained and tested on the same cohort. ENLIGHT-DeepPT future application could provide clinicians with rapid treatment recommendations to an array of different therapies and importantly, may contribute to advancing precision oncology in developing countries.
RESUMO
Genetic studies have identified numerous loci associated with type 2 diabetes (T2D), but the functional roles of many loci remain unexplored. Here, we engineered isogenic knockout human embryonic stem cell lines for 20 genes associated with T2D risk. We examined the impacts of each knockout on ß cell differentiation, functions, and survival. We generated gene expression and chromatin accessibility profiles on ß cells derived from each knockout line. Analyses of T2D-association signals overlapping HNF4A-dependent ATAC peaks identified a likely causal variant at the FAIM2 T2D-association signal. Additionally, the integrative association analyses identified four genes (CP, RNASE1, PCSK1N, and GSTA2) associated with insulin production, and two genes (TAGLN3 and DHRS2) associated with ß cell sensitivity to lipotoxicity. Finally, we leveraged deep ATAC-seq read coverage to assess allele-specific imbalance at variants heterozygous in the parental line and identified a single likely functional variant at each of 23 T2D-association signals.
Assuntos
Diabetes Mellitus Tipo 2 , Células-Tronco Embrionárias Humanas , Células Secretoras de Insulina , Humanos , Diabetes Mellitus Tipo 2/genética , Diabetes Mellitus Tipo 2/metabolismo , Células-Tronco Embrionárias Humanas/metabolismo , Predisposição Genética para Doença , Estudo de Associação Genômica Ampla , Células Secretoras de Insulina/metabolismo , Polimorfismo de Nucleotídeo Único , Carbonil Redutase (NADPH)/genética , Carbonil Redutase (NADPH)/metabolismoRESUMO
Genetic studies have identified numerous loci associated with type 2 diabetes (T2D), but the functional role of many loci has remained unexplored. In this study, we engineered isogenic knockout human embryonic stem cell (hESC) lines for 20 genes associated with T2D risk. We systematically examined ß-cell differentiation, insulin production and secretion, and survival. We performed RNA-seq and ATAC-seq on hESC-ß cells from each knockout line. Analyses of T2D GWAS signals overlapping with HNF4A-dependent ATAC peaks identified a specific SNP as a likely causal variant. In addition, we performed integrative association analyses and identified four genes ( CP, RNASE1, PCSK1N and GSTA2 ) associated with insulin production, and two genes ( TAGLN3 and DHRS2 ) associated with sensitivity to lipotoxicity. Finally, we leveraged deep ATAC-seq read coverage to assess allele-specific imbalance at variants heterozygous in the parental hESC line, to identify a single likely functional variant at each of 23 T2D GWAS signals.
RESUMO
Dislocated hip joint is a painful condition, which requires urgent reduction. Previously, ultrasound (US)-guided pericapsular nerve group (PENG) block has been used for reduction of dislocated prosthetic hip. We have used landmark-guided PENG block in two patients of dislocation of prosthetic hip. We suggest that the landmark-guided technique of PENG block can be used safely and successfully as an alternative technique, where US facility is not available.
RESUMO
MRI reconstruction is the fundamental task of obtaining diagnostic quality images from MRI sensor data and is an active area of research for improving accuracy, speed and memory requirements of the process. Complex-valued neural networks have previously achieved superior MRI reconstructions compared to real-valued nets. But those works operated in the image domain to denoise poor quality reconstructions of the raw sensor (k-space) data. Also small-scale or proprietary datasets with few clinical images or raw k-space volumes were used in these works, and none of the works use publicly available large-scale raw k-space datasets. Recent studies have shown that cross-domain neural networks for MRI reconstruction, or networks which leverage information from both k-space and image domains, have better potential than single-domain networks which operate only in one domain. We study the effects of complex-valued operations on a top-performing cross-domain neural network for MRI reconstruction called the Primal-Dual net, or PD-net. The PD-net is a fully convolutional architecture that takes input as raw k-space data and outputs the reconstructions, thus performing both the inversion and denoising tasks. We experiment with the publicly available, large-scale fastMRI single-coil knee dataset having 973 train volumes and 199 validation volumes. Our proposed method (Complex PD-net) achieves PSNR and SSIM of 33.3 dB and 0.8033 respectively, compared to 32.13 dB and 0.728 obtained by PD-net. Our Complex PD-net achieves 10.3% higher SSIM with just over 50% of the total parameters w.r.t. the SOTA methodology.
Assuntos
Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética , Humanos , Processamento de Imagem Assistida por Computador/métodos , Joelho/diagnóstico por imagem , Articulação do Joelho/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Redes Neurais de ComputaçãoRESUMO
Background and Aims: Truncal blocks play an important role in multimodal analgesia regimens to manage the postoperative pain after lower segment caesarean section (LSCS). This study was aimed to compare the analgesic efficacy of ultrasound (US)-guided transmuscular quadratus lumborum block (TQLB) and thoracic erector spinae plane block (TESPB) in parturients of LSCS done under subarachnoid block (SAB). Methods: In a randomised and double blind study, 60 parturients scheduled for LSCS under spinal anaesthesia were randomly divided into two equal groups: group E (n = 30) and group Q (n = 30). After surgery, each parturient received either US guided bilateral TQLB (group Q) or TESPB (group E) with 20 ml 0.375% ropivacaine and 4 mg dexamethasone on each side. Assessments were done at 2, 4, 6, 8, 10, 12 and 24 h. The primary objective was to compare the duration of analgesia (first request to rescue analgesia) and the secondary objectives were to compare pain scores [numerical rating score (NRS)], total amount of tramadol consumption, incidence of nausea-vomiting, parturient satisfaction and other adverse effects in 24 hours postoperatively. Results: The duration of analgesia (mean ± standard deviation) was comparable in group E (11.90 ± 2.49 h) and group Q (12.56 ± 3.38 h), P = 0.19. Pain scores (NRS) at rest and on movement were comparable at all time points of 2, 4, 6, 8, 10, 12, and 24 h (P > 0.05). The amount of tramadol used was comparable in group E and group Q (P = 0.48). Conclusion: TESPB and TQLB are equally efficacious to provide postoperative analgesia after LSCS done under SAB when used as a part of multimodal analgesia.
RESUMO
The FDA has recently approved a high tumor mutational burden (TMB-high) biomarker, defined by ≥10 mutations/Mb, for the treatment of solid tumors with pembrolizumab, an immune checkpoint inhibitor (ICI) that targets PD1. However, recent studies have shown that this TMB-high biomarker is only able to stratify ICI responders in a subset of cancer types, and the mechanisms underlying this observation have remained unknown. The tumor immune microenvironment (TME) may modulate the stratification power of TMB (termed TMB power), determining if it will be predictive of ICI response in a given cancer type. To systematically study this hypothesis, we inferred the levels of 31 immune-related factors characteristic of the TME of different cancer types in The Cancer Genome Atlas. Integration of this information with TMB and response data of 2,277 patients treated with anti-PD1 identified key immune factors that determine TMB power across 14 different cancer types. We find that high levels of M1 macrophages and low resting dendritic cells in the TME characterized cancer types with high TMB power. A model based on these two immune factors strongly predicted TMB power in a given cancer type during cross-validation and testing (Spearman Rho = 0.76 and 1, respectively). Using this model, we predicted the TMB power in nine additional cancer types, including rare cancers, for which TMB and ICI response data are not yet publicly available. Our analysis indicates that TMB-high may be highly predictive of ICI response in cervical squamous cell carcinoma, suggesting that such a study should be prioritized. SIGNIFICANCE: This study uncovers immune-related factors that may modulate the relationship between high tumor mutational burden and ICI response, which can help prioritize cancer types for clinical trials.
Assuntos
Imunoterapia , Neoplasias , Biomarcadores Tumorais/genética , Humanos , Inibidores de Checkpoint Imunológico/uso terapêutico , Fatores Imunológicos/uso terapêutico , Mutação , Neoplasias/tratamento farmacológico , Neoplasias/terapia , Microambiente Tumoral/genéticaRESUMO
BACKGROUND: Multimodal analgesia (MMA) is the current standard practice to provide post-cesarean analgesia. The aim of this study was to compare the analgesic efficacy of quadratus lumborum (QL) block and transversus abdominis plane (TAP) block as an adjunct to MMA. METHODS: Eighty mothers undergoing cesarean delivery under spinal anesthesia were randomized to receive either TAP or transmuscular QL block (QLB) with 20 mL 0.375% ropivacaine on each side. Postoperatively, all the subjects were assessed at 2, 4, 6, 8, 12, 18, and 24 hours. The primary outcome was the time to first analgesic request. The secondary outcomes were the pain scores during rest and movement, number of doses of tramadol, postoperative nausea-vomiting, sedation, and mother's satisfaction with the pain management. RESULTS: The median (IQR) time to first analgesic request was 12 (9.25, 13) hours in the QL group and 9 (8.25, 11.37) hours in the TAP group (p = 0.0008). Patients in QL group consumed less doses of tramadol than those in TAP group (p < 0.0001). Pain scores were significantly lower in the QL group at all time points (p < 0.0001) except at 8th hour when at rest, p = 0.0024, and on movement, p = 0.0028. The maternal satisfaction was significantly higher in the QL group (p = 0.0017). CONCLUSION: Our study showed the significant delay in time to first analgesic request in QL group patients. Patients in the QL group had lower pain scores, required fewer analgesic supplements, and had more satisfaction. Nausea-vomiting and sedation were comparable.
Assuntos
Analgesia , Tramadol , Músculos Abdominais , Analgésicos Opioides , Método Duplo-Cego , Feminino , Humanos , Dor Pós-Operatória/tratamento farmacológico , Dor Pós-Operatória/prevenção & controle , Náusea e Vômito Pós-Operatórios/induzido quimicamente , Gravidez , Tramadol/uso terapêuticoRESUMO
Prediction of mutational status of different graded glioma is extremely crucial for its diagnosis and treatment planning. Currently FISH and the surgical biopsy techniques are the 'gold standard' in the field of diagnostics; the analyses of which helps to decide appropriate treatment regime. In this study we proposed a novel approach to analyze structural MRI image signature pattern for predicting 1p/19q co-deletion status non-invasively. A total of 159 patients with grade-II and grade-III glioma were included in the analysis. These patients earlier underwent biopsy; the report of which confirmed 57 cases with no 1p/19q co-deletion and 102 cases with 1p/19q co-deletion. Tumor tissue heterogeneity was investigated by variance of cross correlation (VoCC). Significant differences in the pattern of VoCC between two classes was quantified using Lomb-Scargle (LS) periodogram. Energy and the cut-off frequency of LS power spectral density were derived and utilized as the features for classification. RUSBoost classifier was used that yield highest classification accuracy of 84% for G-II and 87% for G-III glioma respectively in classifying 1p/19q co-deleted and 1p/19q non-deleted glioma. In clinical practice the proposed technique can be utilized as a non-invasive pre-confirmatory test of glioma mutation, before wet-lab validation.
Assuntos
Neoplasias Encefálicas/genética , Deleção Cromossômica , Cromossomos Humanos Par 19/genética , Cromossomos Humanos Par 1/genética , Glioma/genética , Imageamento por Ressonância Magnética/métodos , Neoplasias Encefálicas/diagnóstico por imagem , Neoplasias Encefálicas/patologia , Glioma/diagnóstico por imagem , Glioma/patologia , HumanosRESUMO
In this paper, we propose a novel encoder-decoder based surgical phase classification technique leveraging on the spatio-temporal features extracted from the videos of laparoscopic cholecystectomy surgery. We use combined margin loss function to train on the computationally efficient PeleeNet architecture to extract features that exhibit: (1) Intra-phase similarity, (2) Inter-phase dissimilarity. Using these features, we propose to encapsulate sequential feature embeddings, 64 at a time and classify the surgical phase based on customized efficient residual factorized CNN architecture (ST-ERFNet). We obtained surgical phase classification accuracy of 86.07% on the publicly available Cholec80 dataset which consists of 7 surgical phases. The number of parameters required for the computation is approximately reduced by 84% and yet achieves comparable performance as the state of the art.Clinical relevance- Autonomous surgical phase classification sets the platform for automatically analyzing the entire surgical work flow. Additionally, could streamline the process of assessment of a surgery in terms of efficiency, early detection of errors or deviation from usual practice. This would potentially result in increased patient care.
Assuntos
Colecistectomia Laparoscópica , Laparoscopia , Humanos , Redes Neurais de Computação , Fluxo de TrabalhoRESUMO
In this paper, a study is reported on the popular BraTS dataset for segmentation of brain tumor. The BraTS 2019 dataset is used that comprises four MR modalities along with the ground-truth for 259 high grade glioma (HGG) and 76 low grade glioma (LGG) patient data. We have employed U-Net architecture based 2D convolutional neural network (CNN) for each of the orthogonal planes (sagittal, coronal and axial) and fused their predictions. The objective function is aimed to minimize Dice loss between the binary prediction and its actual labels. Samples having tumor information are considered for each patient data to avoid training on non-informative data. The models are trained on 222 HGG data and tested on 37 HGG data using performance metrics such as sensitivity, specificity, accuracy and Dice score. Test-time augmentation is also performed to improve the segmentation performance. 7-fold cross validation is conducted to analyze the performance on different sets of training and testing data.
Assuntos
Glioma , Processamento de Imagem Assistida por Computador , Encéfalo , Glioma/diagnóstico por imagem , Humanos , Imageamento por Ressonância Magnética , Redes Neurais de ComputaçãoRESUMO
BACKGROUND AND AIMS: Regional analgesic techniques such as supra-inguinal fascia-iliaca compartment block (S-FICB) and pericapsular nerve group (PENG) block have been found to be effective in providing good pain relief in hip-fracture patients. However, comparative studies between PENG and S-FICB are lacking. The aim of this study was to compare the analgesic efficacy of S-FICB and PENG block and assess their efficacy in optimal patient positioning for spinal anaesthesia. METHODS: A prospective randomised double-blind study was conducted in 66 patients randomly divided to receive either S-FICB or PENG block under ultrasound guidance. Primary outcome measures were numerical rating scale (NRS) pain score at rest and on passive 15° limb lifting, 30 minutes after the block and ease of spinal positioning. The secondary outcome measures were NRS over 24 hours, amount of tramadol used (number of rescue doses), patients' satisfaction and block-related complications. The results were analysed using statistical software (MedCalc version 19.2.1). Continuous and categorical data were analysed using appropriate statistical analysis and P < 0.05 was considered significant. RESULTS: Post-block, the NRS score decreased significantly in PENG and S-FICB groups at rest and movement (P < 0.0001). The EOSP score was significantly better in PENG group (P < 0.0001). First analgesic request and pain relief in the first 24-hour period were similar between the groups (P = 0.524). CONCLUSION: PENG block provided better pain relief and ease of positing during SA in patients with fractured hip scheduled for hip surgery.
RESUMO
Deciphering the post-transcriptional mechanisms (PTM) regulating gene expression is critical to understand the dynamics underlying transcriptomic regulation in cancer. Alternative polyadenylation (APA)-regulation of mRNA 3'UTR length by alternating poly(A) site usage-is a key PTM mechanism whose comprehensive analysis in cancer remains an important open challenge. Here we use a method and analysis pipeline that sequences 3'end-enriched RNA directly to overcome the saturation limitation of traditional 5'-3' based sequencing. We comprehensively map the APA landscape in lung cancer in a cohort of 98 tumor/non-involved tissues derived from European American and African American patients. We identify a global shortening of 3'UTR transcripts in lung cancer, with notable functional implications on the expression of both coding and noncoding genes. We find that APA of non-coding RNA transcripts (long non-coding RNAs and microRNAs) is a recurrent event in lung cancer and discover that the selection of alternative polyA sites is a form of non-coding RNA expression control. Our results indicate that mRNA transcripts from EAs are two times more likely than AAs to undergo APA in lung cancer. Taken together, our findings comprehensively map and identify the important functional role of alternative polyadenylation in determining transcriptomic heterogeneity in lung cancer.